Update app.py

app.py

@@ -100,12 +100,22 @@ st.markdown("""
 # Display large logo at the top of the main page
 st.image("https://i.postimg.cc/2j0QWF3Z/Removal-575.png", width=390)
 
+# Set Streamlit app title
+st.title("WebChatter 💬")
 
 # Initialize session state
 if "index_created" not in st.session_state:
     st.session_state.index_created = False
 if "url_content" not in st.session_state:
     st.session_state.url_content = None
+if "vectorstore" not in st.session_state:
+    st.session_state.vectorstore = None
+if "summary" not in st.session_state:
+    st.session_state.summary = None
+
+# Initialize embeddings once at the start
+if "embeddings" not in st.session_state:
+    st.session_state.embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
 # Sidebar for URL input
 with st.sidebar:
@@ -187,24 +197,29 @@ if process_url_clicked:
                     st.text(f"Split into {len(docs)} document chunks.")
 
                     st.text("Embedding Vector Started Building...✅✅✅")
-                    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-                    vectorstore_openai = FAISS.from_documents(docs, embeddings)
+                    embeddings = st.session_state.embeddings
+                    vectorstore = FAISS.from_documents(docs, embeddings)
 
                     faiss_index_path = "faiss_index"
-                    save_faiss_index(vectorstore_openai, faiss_index_path)
+                    save_faiss_index(vectorstore, faiss_index_path)
+                    st.session_state.vectorstore = vectorstore  # Cache the vectorstore
                     st.session_state.index_created = True
                     st.text("FAISS index saved successfully! ✅✅✅")
                     time.sleep(2)
                 except Exception as e:
                     st.error(f"Error processing URL: {str(e)}")
 
-# Display summary if content is available
-if st.session_state.url_content:
+# Summary button
+with main_container:
+    if st.session_state.url_content and st.button("Generate Summary"):
+        with st.spinner("Generating summary..."):
+            st.session_state.summary = summarize_content(st.session_state.url_content, llm)
+
+# Display summary if generated
+if st.session_state.summary:
     with main_container:
         st.header("Summary of the URL Content")
-        with st.spinner("Generating summary..."):
-            summary = summarize_content(st.session_state.url_content, llm)
-            st.write(summary)
+        st.write(st.session_state.summary)
 
 # Query input with Ask button
 with main_container:
@@ -214,16 +229,14 @@ with main_container:
 
 if ask_clicked and query:
     with main_container:
-        if not st.session_state.index_created or not os.path.exists("faiss_index"):
+        if not st.session_state.index_created or st.session_state.vectorstore is None:
             st.error("No FAISS index found. Please process a URL first.")
         else:
             with st.spinner("Processing your question..."):
                 try:
-                    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-                    vectorstore = load_faiss_index("faiss_index", embeddings)
                     chain = RetrievalQAWithSourcesChain.from_llm(
                         llm=llm,
-                        retriever=vectorstore.as_retriever(),
+                        retriever=st.session_state.vectorstore.as_retriever(search_kwargs={"k": 2}),  # Limit to top 2 documents
                         question_prompt=qa_prompt
                     )
                     result = chain({"question": query}, return_only_outputs=True)